User Tools

Site Tools


projects:year4:15.3

15.3 - Big Data Analysis in Social Media Applications

Project - Summary

The main goal of this project is to develop a unifying platform for integrating, analyzing and visualizing various social media platforms, develop analytical tools and solutions for data cleansing, message annotation, classification and clustering, topic evolution, and recommendation for social media users. The Drexel team will focus on integration of social media data sets and developing novel algorithms in analyzing and visualization high dimensional big data in a dynamic environment. Tampere University will focus on integration of multimedia indexing and retrieval techniques for Big Data Analysis in Social Media applications by enabling partitioning massive volumes of Big (multimedia) Data into small and homogenous sets that are both “learnable” and “manageable” in the most efficient way possible. In order to reach the targeted goal we will have the following objectives:

  • Enhance previous work to detect emerging practices, recommendation and collaborative filtering.
  • Develop programming interfaces and implementations for data cleansing, message annotation, classification and clustering, topic evolution, and recommendation.
  • Develop content management and learning for multimedia “Big Data” based on holistic “Divide & Conquer” philosophy.
  • Perform a distributed computing and storage platform for content management and preservation.
  • Research and develop, ever-evolving and self-adapting clouds of evolutionary features synthesizers and classifier networks to “learn” and “mimic” the human audio-visual system based categorization for the audio-visual content.
  • Study user roles, content, and temporal thread evolution in multimodal environments (e.g., thread-based commenting).
  • Develop a representation framework (language, inference algorithms) and computational models that accurately capture the nuances on online behavior, enabling automated reasoning (e.g., prediction of thread evolution, intervention planning).

Project - Team

Team Member Role Email Phone Number Academic Site/IAB
Xiaohua Tony Hu PI Not available Not available Drexel University
Moncef Gabbouj PI Not available Not available Tampere University
Serkan Kiranyaz Co-PI Not available Not available Tampere University
Mengwen Liu PhD Student Not available Not available Drexel University
Xiaoli Song PhD Student Not available Not available Drexel University
Ezgi Can Ozan PhD Student Not available Not available Tampere University

Project - Impact and Uses/Benefits

The developed concept is beneficial for social media users and analysts in various ways, First, this new relation between the social media posts provides a brand new source of information for the analysts to investigate. Combined with the text information, it is expected to reach to a deeper understanding of social media. For the users, the proposed method provides an easier and faster access to desired information.

Project - Deep Dive

Project - Documents

FilenameFilesizeLast modified
15.3_year_4_presentation.pptx2.2 MiB2019/08/22 11:50
15.3_year_4_executive_summary.pdf175.3 KiB2019/08/22 11:50
15.3_year_4_quad_chart.pptx1.3 MiB2019/08/22 11:50
15.3_year_4_ip_letter_combined.pdf371.0 KiB2019/08/22 11:50
15.3_year_4_final_report.pdf1.1 MiB2019/08/22 10:33
projects/year4/15.3.txt · Last modified: 2021/07/27 15:54 by sally.johnson